Shadowgraph
About
Sign in

jackhhao/jailbreak-classifier

Model

24

stars

6

commits

10

repos using this model

2

linked in READMEs

Apr 5, 2024

updated

bert
endpoints_compatible
jailbreak
moderation
prompt-injection
pytorch
security
text-classification
text-embeddings-inference
transformers
Browse cluster: Transformer Text Classification & Embeddings →

README

Jailbreak Classifier

Classifies prompts as jailbreaks or benign. This is a fine-tune checkpoint of bert-base-uncased on the jailbreak-classification dataset.

Training Details

Training Data

Fine-tuned on the jailbreak-classification dataset.

Training Procedure

Training Hyperparameters

Fine-tuning hyper-parameters:

  • learning_rate = 5e-5
  • train_batch_size = 8
  • eval_batch_size = 8
  • lr_scheduler_type = linear
  • num_train_epochs = 5.0

Contributors

jackhhao

6 commits

Similar repos

rogue-security/prompt-injection-jailbreak-sentinel-v2

Model

39

shared topics

jackhhao/jailbreak-classification

Dataset

82

shared topics

moarslan/bert-base-turkish-sentiment-analysis

Model

0

shared topics

IlyaGusev/rubertconv_toxic_clf

Model

15

shared topics

Securelayer7/promptpurify

Model

0

shared topics

Hate-speech-CNERG/english-abusive-MuRIL

Model

6

shared topics

Hate-speech-CNERG/bengali-abusive-MuRIL

Model

1

shared topics

Hate-speech-CNERG/hindi-codemixed-abusive-MuRIL

Model

0

shared topics

Used in code

Praveengovianalytics/falcon-evaluate

Falcon Evaluate is an open-source Python library aims to revolutionise the LLM - RAG evaluation…

16

1 file

dronefreak/PromptScreen

Protect your LLMs from prompt injection and jailbreak attacks. Easy-to-use Python package with…

15

1 file

karloks2005/JailbreakLab

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial…

10

1 file

leomaurodesenv/big-qa-architecture

Safeguarding Big Data Question-Answering Systems

2

1 file

ElvenLullaby/Checkpoint4-AI-ML

0

1 file

cyber-evangelists/threat-mon-rag

Threat Mon Rag to Demonstrate the Rag for security researchers.

0

1 file

yjbae3974/FastFour_jailbreak

0

1 file

pavann19/Gatekeeper-AI-Infrastructure-and-Governance-Gateway

0

1 file

harshitsaini17/controlplane-ai

ControlPlane.ai — real-time AI oversight gateway. Per-use-case policy config decides…

0

1 file

NextShiftConsulting/swarm-it-adk

Swarm It: The observability platform for AI agent swarms - monitor coordination, detect drift, and…

0

1 file

Linked in READMEs

karloks2005/JailbreakLab

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial…

10

README badge

guardrails-ai/detect_jailbreak

Prototype Jailbreak Detection Guard

5

README badge

jackhhao/jailbreak-classifier

Model

24

stars

6

commits

10

repos using this model

2

linked in READMEs

Apr 5, 2024

updated

bert
endpoints_compatible
jailbreak
moderation
prompt-injection
pytorch
security
text-classification
text-embeddings-inference
transformers
Browse cluster: Transformer Text Classification & Embeddings →

README

Jailbreak Classifier

Classifies prompts as jailbreaks or benign. This is a fine-tune checkpoint of bert-base-uncased on the jailbreak-classification dataset.

Training Details

Training Data

Fine-tuned on the jailbreak-classification dataset.

Training Procedure

Training Hyperparameters

Fine-tuning hyper-parameters:

  • learning_rate = 5e-5
  • train_batch_size = 8
  • eval_batch_size = 8
  • lr_scheduler_type = linear
  • num_train_epochs = 5.0

Similar repos

rogue-security/prompt-injection-jailbreak-sentinel-v2

Model

39

shared topics

jackhhao/jailbreak-classification

Dataset

82

shared topics

moarslan/bert-base-turkish-sentiment-analysis

Model

0

shared topics

IlyaGusev/rubertconv_toxic_clf

Model

15

shared topics

Securelayer7/promptpurify

Model

0

shared topics

Hate-speech-CNERG/english-abusive-MuRIL

Model

6

shared topics

Hate-speech-CNERG/bengali-abusive-MuRIL

Model

1

shared topics

Hate-speech-CNERG/hindi-codemixed-abusive-MuRIL

Model

0

shared topics

Used in code

Praveengovianalytics/falcon-evaluate

Falcon Evaluate is an open-source Python library aims to revolutionise the LLM - RAG evaluation…

16

1 file

dronefreak/PromptScreen

Protect your LLMs from prompt injection and jailbreak attacks. Easy-to-use Python package with…

15

1 file

karloks2005/JailbreakLab

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial…

10

1 file

leomaurodesenv/big-qa-architecture

Safeguarding Big Data Question-Answering Systems

2

1 file

ElvenLullaby/Checkpoint4-AI-ML

0

1 file

cyber-evangelists/threat-mon-rag

Threat Mon Rag to Demonstrate the Rag for security researchers.

0

1 file

yjbae3974/FastFour_jailbreak

0

1 file

pavann19/Gatekeeper-AI-Infrastructure-and-Governance-Gateway

0

1 file

harshitsaini17/controlplane-ai

ControlPlane.ai — real-time AI oversight gateway. Per-use-case policy config decides…

0

1 file

NextShiftConsulting/swarm-it-adk

Swarm It: The observability platform for AI agent swarms - monitor coordination, detect drift, and…

0

1 file

Linked in READMEs

karloks2005/JailbreakLab

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial…

10

README badge

guardrails-ai/detect_jailbreak

Prototype Jailbreak Detection Guard

5

README badge

Contributors

jackhhao

6 commits